Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
The algo based on AI is trade's future

Why the algo based on AI is trade's future?
First, the stock price is nonlinear. too early to entering, we will meet false signal. too lately to entering, we will lost profit opportunity. traditional way is linear, but AI have some nonlinear solution. Second, peoples have their own strategic preference. for example, golden cross algo, someone like use 5/20 days, someone like use 7/15 days, which is better? I do not know. sometimes this work, sometimes it not. better let AI to self-adapt the algo parameter. Third, the world is faster, the data is bigger, the more complex relevance need AI technology to help us to do some basic work for trade strategic.

What problem we have now?
Usually we use machine learning to realize AI. but the time series analysis technology is a difficult problem, even famous scikit-learn have a few good solution for that. That is all? no, no, no... it is challenges, also is opportunities, we are stand at dawn. Let us change thinking, program = data + algo, since there is no good machine learning, we can do some data pretreated, map time series analysis into space problem, then can make usual machine learning more useful.

1 response

Share three power auto machine learning tools, the test result is amazing.

1.Auto-sklearn provides out-of-the-box supervised machine learning. Built around the scikit-learn machine learning library, auto-sklearn automatically searches for the right learning algorithm for a new machine learning dataset and optimizes its hyperparameters. Thus, it frees the machine learning practitioner from these tedious tasks and allows her to focus on the real problem.

2.TPOT is a Python tool that automatically creates and optimizes machine learning pipelines using genetic programming.TPOT will automate the most tedious part of machine learning by intelligently exploring thousands of possible pipelines to find the best one for your data.

3.hyperopt is a Python library for optimizing over awkward search spaces with real-valued, discrete, and conditional dimensions.

I believe, the algo based on AI is trade's future.